sianbru's picture
Model save
62d0136
metadata
license: apache-2.0
base_model: bert-base-multilingual-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: bert_product_classifier_name
    results: []

bert_product_classifier_name

This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3406
  • Accuracy: 0.9517
  • F1: 0.9513
  • Precision: 0.9514
  • Recall: 0.9517

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.8574 1.0 960 0.3075 0.9079 0.9069 0.9077 0.9079
0.267 2.0 1920 0.2432 0.9292 0.9294 0.9307 0.9292
0.1596 3.0 2880 0.2228 0.9411 0.9408 0.9409 0.9411
0.1094 4.0 3840 0.2540 0.9452 0.9447 0.9447 0.9452
0.0755 5.0 4800 0.2652 0.9470 0.9471 0.9472 0.9470
0.0506 6.0 5760 0.2924 0.9492 0.9491 0.9491 0.9492
0.0364 7.0 6720 0.3251 0.9475 0.9470 0.9476 0.9475
0.022 8.0 7680 0.3271 0.9518 0.9515 0.9514 0.9518
0.0122 9.0 8640 0.3368 0.9522 0.9520 0.9519 0.9522
0.0103 10.0 9600 0.3406 0.9517 0.9513 0.9514 0.9517

Framework versions

  • Transformers 4.32.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3